Prabha Srinivasagam

Dr. Prabha Srinivasagam


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2020 in Applied Soft Computing
Verified
Journal Article
Closed access
DCD. Chitradevi
D. Chitradevi
PSPrabha Srinivasagam
Prabha Srinivasagam

1 December 2024 in Annals of Translational Medicine
Verified
Journal Article
Open access
PDF file
Ariana GenoveseAriana Genovese
Ariana Genovese
SBSahar Borna
Sahar Borna
CCCesar Abraham Gomez Cabello
Cesar Abraham Gomez Cabello
Syed Ali HaiderSyed Ali Haider
Syed Ali Haider
PSPrabha Srinivasagam
Prabha Srinivasagam
BVBenjamin R. Veenstra
Benjamin R. Veenstra
Background: Addressing language barriers through accurate interpretation is crucial for providing quality care and establishing trust. While the ability of artificial intelligence (AI) to translate medical documentation has been studied, its role for patient-provider communication is less explored. This review evaluates AI’s effectiveness in clinical translation by assessing accuracy, usability, satisfaction, and feedback on its use. Methods: A systematic search was conducted on July 11, 2024, across Cumulated Index in Nursing and Allied Health Literature (CINAHL), Institute of Electrical and Electronics Engineers (IEEE) Xplore, PubMed, Scopus, Web of Science, and Google Scholar. Inclusion criteria required AI to translate clinical information for a real or theoretical consultation. Exclusion criteria included reviews, correspondence, educational materials, non-peer-reviewed or retracted reports, non-English translations, pre-2016 publications, and reports on sign language or patient education. Search strings representing AI, language interpretation, and healthcare were used. Two investigators independently conducted the screening, extraction, synthesis of results, and bias assessments using Risk Of Bias In Non-randomized Studies - of Interventions (ROBINS-I), Mixed Methods Appraisal Tool (MMAT), and the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Qualitative Research. A third investigator resolved conflicts. Results: Of 1,095 reports, 9 studies were analyzed, evaluating AI translation platforms Google Translate, Microsoft Translator, Apple iTranslate, AwezaMed, Pocketalk W, and the Asynchronous Telepsychiatry (ATP) App. Investigations occurred in the US, France, Switzerland, and South Africa, with publications from 2019–2024. AI medical translation shows promise, typically providing accurate translations for brief communications in limited languages, though human translation is often necessary. Accuracy scores ranged from 83–97.8% when translating from English, and 36–76% when translating to English. Usability scores were 76.7–96.7%. Patients were more satisfied than clinicians, with 84–96.6% and 53.8–86.7% satisfied, respectively. Clinicians were hesitant to use AI due to questions of respect, quality, reliability, and misunderstanding. AI is being used as a last-resort option, to assist fluent, non-certified providers and lay interpreters, and for brief communications. Conclusions: Limitations include few languages tested, unidirectional translation, simulation, and evolving translation tools. AI shows promise in clinical translation, but the complexity of medical consultations requires a balanced approach combining AI and human translation services for quality care.

30 August 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
Yunguo YuYunguo Yu
Yunguo Yu
CCCesar Abraham Gomez Cabello
Cesar Abraham Gomez Cabello
Syed Ali HaiderSyed Ali Haider
Syed Ali Haider
Ariana GenoveseAriana Genovese
Ariana Genovese
PSPrabha Srinivasagam
Prabha Srinivasagam
Antonio Jorge ForteAntonio Jorge Forte
Antonio Jorge Forte
Background: Artificial Intelligence (AI)-driven Decision Support Systems (DSSs) promise improvements in diagnostic accuracy and clinical workflow efficiency, but their adoption is hindered by inadequate confidence calibration, limited transparency, and poor alignment with real-world decision processes, which limit clinician trust and lead to high override rates. Methods: We developed and validated a dynamic scoring framework to enhance trust in AI-generated diagnoses by integrating AI confidence scores, semantic similarity measures, and transparency weighting into the override decision process using 6689 cardiovascular cases from the MIMIC-III dataset. Override thresholds were calibrated and validated across varying transparency and confidence levels, with override rate as the primary acceptance measure. Results: The implementation of this framework reduced the override rate to 33.29%, with high-confidence predictions (90–99%) overridden at a rate of only 1.7%, and low-confidence predictions (70–79%) at a rate of 99.3%. Minimal transparency diagnoses had a 73.9% override rate compared to 49.3% for moderate transparency. Statistical analyses confirmed significant associations between confidence, transparency, and override rates (p < 0.001). Conclusions: These findings suggest that enhanced transparency and confidence calibration can substantially reduce override rates and promote clinician acceptance of AI diagnostics. Future work should focus on clinical validation to optimize patient safety, diagnostic accuracy, and efficiency.

16 May 2020 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
DDDr. Chitradevi D
Dr. Chitradevi D
PSPrabha Srinivasagam
Prabha Srinivasagam
APAlex Daniel Prabhu Arul Pitchai
Alex Daniel Prabhu Arul Pitchai

10 July 2025 in Sensors
Verified
Journal Article
Open access
PDF file
Syed Ali HaiderSyed Ali Haider
Syed Ali Haider
PSPrabha Srinivasagam
Prabha Srinivasagam
CCCesar Abraham Gomez Cabello
Cesar Abraham Gomez Cabello
SBSahar Borna
Sahar Borna
Ariana GenoveseAriana Genovese
Ariana Genovese
Antonio Jorge ForteAntonio Jorge Forte
Antonio Jorge Forte
Background: Data accessibility remains a significant barrier in healthcare AI due to privacy constraints and logistical challenges. Synthetic data, which mimics real patient information while remaining both realistic and non-identifiable, offers a promising solution. Large Language Models (LLMs) create new opportunities to generate high-fidelity clinical conversations between patients and physicians. However, the value of this synthetic data depends on careful evaluation of its realism, accuracy, and practical relevance. Objective: To assess the performance of four leading LLMs: ChatGPT 4.5, ChatGPT 4o, Claude 3.7 Sonnet, and Gemini Pro 2.5 in generating synthetic transcripts of patient–physician interactions in plastic surgery scenarios. Methods: Each model generated transcripts for ten plastic surgery scenarios. Transcripts were independently evaluated by three clinically trained raters using a seven-criterion rubric: Medical Accuracy, Realism, Persona Consistency, Fidelity, Empathy, Relevancy, and Usability. Raters were blinded to the model identity to reduce bias. Each was rated on a 5-point Likert scale, yielding 840 total evaluations. Descriptive statistics were computed, and a two-way repeated measures ANOVA was used to test for differences across models and metrics. In addition, transcripts were analyzed using automated linguistic and content-based metrics. Results: All models achieved strong performance, with mean ratings exceeding 4.5 across all criteria. Gemini 2.5 Pro received mean scores (5.00 ± 0.00) in Medical Accuracy, Realism, Persona Consistency, Relevancy, and Usability. Claude 3.7 Sonnet matched the scores in Persona Consistency and Relevancy and led in Empathy (4.96 ± 0.18). ChatGPT 4.5 also achieved perfect scores in Relevancy, with high scores in Empathy (4.93 ± 0.25) and Usability (4.96 ± 0.18). ChatGPT 4o demonstrated consistently strong but slightly lower performance across most dimensions. ANOVA revealed no statistically significant differences across models (F(3, 6) = 0.85, p = 0.52). Automated analysis showed substantial variation in transcript length, style, and content richness: Gemini 2.5 Pro generated the longest and most emotionally expressive dialogues, while ChatGPT 4o produced the shortest and most concise outputs. Conclusions: Leading LLMs can generate medically accurate, emotionally appropriate synthetic dialogues suitable for educational and research use. Despite high performance, demographic homogeneity in generated patients highlights the need for improved diversity and bias mitigation in model outputs. These findings support the cautious, context-aware integration of LLM-generated dialogues into medical training, simulation, and research.

28 December 2024 in Bioengineering
Verified
Journal Article
Open access
PDF file
Yunguo YuYunguo Yu
Yunguo Yu
CCCesar Abraham Gomez Cabello
Cesar Abraham Gomez Cabello
SMSvetlana Makarova
Svetlana Makarova
YPYogesh Parte
Yogesh Parte
SBSahar Borna
Sahar Borna
Antonio Jorge ForteAntonio Jorge Forte
Antonio Jorge Forte
Current clinical care relies heavily on complex, rule-based systems for tasks like diagnosis and treatment. However, these systems can be cumbersome and require constant updates. This study explores the potential of the large language model (LLM), LLaMA 2, to address these limitations. We tested LLaMA 2′s performance in interpreting complex clinical process models, such as Mayo Clinic Care Pathway Models (CPMs), and providing accurate clinical recommendations. LLM was trained on encoded pathways versions using DOT language, embedding them with SentenceTransformer, and then presented with hypothetical patient cases. We compared the token-level accuracy between LLM output and the ground truth by measuring both node and edge accuracy. LLaMA 2 accurately retrieved the diagnosis, suggested further evaluation, and delivered appropriate management steps, all based on the pathways. The average node accuracy across the different pathways was 0.91 (SD ± 0.045), while the average edge accuracy was 0.92 (SD ± 0.122). This study highlights the potential of LLMs for healthcare information retrieval, especially when relevant data are provided. Future research should focus on improving these models’ interpretability and their integration into existing clinical workflows.